Abstract
Artificial intelligence (AI) is gaining momentum in earth sciences as a tool to analyze complex natural hazards and their impacts. Such analyses are critical for effective Early Warning Systems (EWSs), which is aiming to generate timely and actionable risk information to protect sectors, systems, and people. Despite advancements in AI, its role in EWS remains underexplored across the four pillars of the Early Warning for All (EW4All) framework; risk knowledge, forecasting, warning dissemination and communication and response preparedness. This study draws on a systematic literature review to assess AI methods utilized in the context of EWS, examines their challenges and opportunities and discusses guiding questions for responsible use. Our study highlights key gaps across knowledge, application and policy. Moreover, we call for coordinated efforts to develop responsible AI frameworks that enhance EWS while ensuring they remain inclusive, accessible, and people-centred that ultimately supports the goal of EW4All by 2027.